linux/mm/util.c

1180 lines
29 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-16 23:30:54 +00:00
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mman.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
#include <linux/userfaultfd_k.h>
mm, fs: move randomize_stack_top from fs to mm Patch series "Provide generic top-down mmap layout functions", v6. This series introduces generic functions to make top-down mmap layout easily accessible to architectures, in particular riscv which was the initial goal of this series. The generic implementation was taken from arm64 and used successively by arm, mips and finally riscv. Note that in addition the series fixes 2 issues: - stack randomization was taken into account even if not necessary. - [1] fixed an issue with mmap base which did not take into account randomization but did not report it to arm and mips, so by moving arm64 into a generic library, this problem is now fixed for both architectures. This work is an effort to factorize architecture functions to avoid code duplication and oversights as in [1]. [1]: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1429066.html This patch (of 14): This preparatory commit moves this function so that further introduction of generic topdown mmap layout is contained only in mm/util.c. Link: http://lkml.kernel.org/r/20190730055113.23635-2-alex@ghiti.fr Signed-off-by: Alexandre Ghiti <alex@ghiti.fr> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Burton <paul.burton@mips.com> Cc: James Hogan <jhogan@kernel.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-23 22:38:37 +00:00
#include <linux/elf.h>
#include <linux/elf-randomize.h>
#include <linux/personality.h>
mm, fs: move randomize_stack_top from fs to mm Patch series "Provide generic top-down mmap layout functions", v6. This series introduces generic functions to make top-down mmap layout easily accessible to architectures, in particular riscv which was the initial goal of this series. The generic implementation was taken from arm64 and used successively by arm, mips and finally riscv. Note that in addition the series fixes 2 issues: - stack randomization was taken into account even if not necessary. - [1] fixed an issue with mmap base which did not take into account randomization but did not report it to arm and mips, so by moving arm64 into a generic library, this problem is now fixed for both architectures. This work is an effort to factorize architecture functions to avoid code duplication and oversights as in [1]. [1]: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1429066.html This patch (of 14): This preparatory commit moves this function so that further introduction of generic topdown mmap layout is contained only in mm/util.c. Link: http://lkml.kernel.org/r/20190730055113.23635-2-alex@ghiti.fr Signed-off-by: Alexandre Ghiti <alex@ghiti.fr> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Burton <paul.burton@mips.com> Cc: James Hogan <jhogan@kernel.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-23 22:38:37 +00:00
#include <linux/random.h>
#include <linux/processor.h>
#include <linux/sizes.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
#include "internal.h"
mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda <a.hajda@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mike Turquette <mturquette@linaro.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Greg KH <greg@kroah.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 22:36:24 +00:00
/**
* kfree_const - conditionally free memory
* @x: pointer to the memory
*
* Function calls kfree only if @x is not in .rodata section.
*/
void kfree_const(const void *x)
{
if (!is_kernel_rodata((unsigned long)x))
kfree(x);
}
EXPORT_SYMBOL(kfree_const);
/**
* kstrdup - allocate space for and copy an existing string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Return: newly allocated copy of @s or %NULL in case of error
*/
char *kstrdup(const char *s, gfp_t gfp)
{
size_t len;
char *buf;
if (!s)
return NULL;
len = strlen(s) + 1;
buf = kmalloc_track_caller(len, gfp);
if (buf)
memcpy(buf, s, len);
return buf;
}
EXPORT_SYMBOL(kstrdup);
mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda <a.hajda@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mike Turquette <mturquette@linaro.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Greg KH <greg@kroah.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 22:36:24 +00:00
/**
* kstrdup_const - conditionally duplicate an existing const string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Note: Strings allocated by kstrdup_const should be freed by kfree_const and
* must not be passed to krealloc().
*
* Return: source string if it is in .rodata section otherwise
* fallback to kstrdup.
mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda <a.hajda@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mike Turquette <mturquette@linaro.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Greg KH <greg@kroah.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 22:36:24 +00:00
*/
const char *kstrdup_const(const char *s, gfp_t gfp)
{
if (is_kernel_rodata((unsigned long)s))
return s;
return kstrdup(s, gfp);
}
EXPORT_SYMBOL(kstrdup_const);
/**
* kstrndup - allocate space for and copy an existing string
* @s: the string to duplicate
* @max: read at most @max chars from @s
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Note: Use kmemdup_nul() instead if the size is known exactly.
*
* Return: newly allocated copy of @s or %NULL in case of error
*/
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
size_t len;
char *buf;
if (!s)
return NULL;
len = strnlen(s, max);
buf = kmalloc_track_caller(len+1, gfp);
if (buf) {
memcpy(buf, s, len);
buf[len] = '\0';
}
return buf;
}
EXPORT_SYMBOL(kstrndup);
/**
* kmemdup - duplicate region of memory
*
* @src: memory region to duplicate
* @len: memory region length
* @gfp: GFP mask to use
*
* Return: newly allocated copy of @src or %NULL in case of error
*/
void *kmemdup(const void *src, size_t len, gfp_t gfp)
{
void *p;
p = kmalloc_track_caller(len, gfp);
if (p)
memcpy(p, src, len);
return p;
}
EXPORT_SYMBOL(kmemdup);
/**
* kmemdup_nul - Create a NUL-terminated string from unterminated data
* @s: The data to stringify
* @len: The size of the data
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Return: newly allocated copy of @s with NUL-termination or %NULL in
* case of error
*/
char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
{
char *buf;
if (!s)
return NULL;
buf = kmalloc_track_caller(len + 1, gfp);
if (buf) {
memcpy(buf, s, len);
buf[len] = '\0';
}
return buf;
}
EXPORT_SYMBOL(kmemdup_nul);
/**
* memdup_user - duplicate memory region from user space
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Return: an ERR_PTR() on failure. Result is physically
* contiguous, to be freed by kfree().
*/
void *memdup_user(const void __user *src, size_t len)
{
void *p;
p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kfree(p);
return ERR_PTR(-EFAULT);
}
return p;
}
EXPORT_SYMBOL(memdup_user);
/**
* vmemdup_user - duplicate memory region from user space
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Return: an ERR_PTR() on failure. Result may be not
* physically contiguous. Use kvfree() to free.
*/
void *vmemdup_user(const void __user *src, size_t len)
{
void *p;
p = kvmalloc(len, GFP_USER);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kvfree(p);
return ERR_PTR(-EFAULT);
}
return p;
}
EXPORT_SYMBOL(vmemdup_user);
/**
* strndup_user - duplicate an existing string from user space
* @s: The string to duplicate
* @n: Maximum number of bytes to copy, including the trailing NUL.
*
* Return: newly allocated copy of @s or an ERR_PTR() in case of error
*/
char *strndup_user(const char __user *s, long n)
{
char *p;
long length;
length = strnlen_user(s, n);
if (!length)
return ERR_PTR(-EFAULT);
if (length > n)
return ERR_PTR(-EINVAL);
p = memdup_user(s, length);
if (IS_ERR(p))
return p;
p[length - 1] = '\0';
return p;
}
EXPORT_SYMBOL(strndup_user);
/**
* memdup_user_nul - duplicate memory region from user space and NUL-terminate
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Return: an ERR_PTR() on failure.
*/
void *memdup_user_nul(const void __user *src, size_t len)
{
char *p;
/*
* Always use GFP_KERNEL, since copy_from_user() can sleep and
* cause pagefault, which makes it pointless to use GFP_NOFS
* or GFP_ATOMIC.
*/
p = kmalloc_track_caller(len + 1, GFP_KERNEL);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kfree(p);
return ERR_PTR(-EFAULT);
}
p[len] = '\0';
return p;
}
EXPORT_SYMBOL(memdup_user_nul);
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev)
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
{
struct vm_area_struct *next;
vma->vm_prev = prev;
if (prev) {
next = prev->vm_next;
prev->vm_next = vma;
} else {
next = mm->mmap;
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
mm->mmap = vma;
}
vma->vm_next = next;
if (next)
next->vm_prev = vma;
}
void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma)
{
struct vm_area_struct *prev, *next;
next = vma->vm_next;
prev = vma->vm_prev;
if (prev)
prev->vm_next = next;
else
mm->mmap = next;
if (next)
next->vm_prev = prev;
}
procfs: mark thread stack correctly in proc/<pid>/maps Stack for a new thread is mapped by userspace code and passed via sys_clone. This memory is currently seen as anonymous in /proc/<pid>/maps, which makes it difficult to ascertain which mappings are being used for thread stacks. This patch uses the individual task stack pointers to determine which vmas are actually thread stacks. For a multithreaded program like the following: #include <pthread.h> void *thread_main(void *foo) { while(1); } int main() { pthread_t t; pthread_create(&t, NULL, thread_main, NULL); pthread_join(t, NULL); } proc/PID/maps looks like the following: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but that is not always a reliable way to find out which vma is a thread stack. Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same content. With this patch in place, /proc/PID/task/TID/maps are treated as 'maps as the task would see it' and hence, only the vma that that task uses as stack is marked as [stack]. All other 'stack' vmas are marked as anonymous memory. /proc/PID/maps acts as a thread group level view, where all thread stack vmas are marked as [stack:TID] where TID is the process ID of the task that uses that vma as stack, while the process stack is marked as [stack]. So /proc/PID/maps will look like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Thus marking all vmas that are used as stacks by the threads in the thread group along with the process stack. The task level maps will however like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] where only the vma that is being used as a stack by *that* task is marked as [stack]. Analogous changes have been made to /proc/PID/smaps, /proc/PID/numa_maps, /proc/PID/task/TID/smaps and /proc/PID/task/TID/numa_maps. Relevant snippets from smaps and numa_maps: [siddhesh@localhost ~ ]$ pgrep a.out 1441 [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack" 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack" 7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2 7fff6273a000 default stack anon=3 dirty=3 N0=3 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack" 7f8a44492000 default stack anon=2 dirty=2 N0=2 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack" 7fff6273a000 default stack anon=3 dirty=3 N0=3 [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix build] Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Jamie Lokier <jamie@shareable.org> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:04 +00:00
/* Check if the vma is being used as a stack by this task */
int vma_is_stack_for_current(struct vm_area_struct *vma)
procfs: mark thread stack correctly in proc/<pid>/maps Stack for a new thread is mapped by userspace code and passed via sys_clone. This memory is currently seen as anonymous in /proc/<pid>/maps, which makes it difficult to ascertain which mappings are being used for thread stacks. This patch uses the individual task stack pointers to determine which vmas are actually thread stacks. For a multithreaded program like the following: #include <pthread.h> void *thread_main(void *foo) { while(1); } int main() { pthread_t t; pthread_create(&t, NULL, thread_main, NULL); pthread_join(t, NULL); } proc/PID/maps looks like the following: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but that is not always a reliable way to find out which vma is a thread stack. Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same content. With this patch in place, /proc/PID/task/TID/maps are treated as 'maps as the task would see it' and hence, only the vma that that task uses as stack is marked as [stack]. All other 'stack' vmas are marked as anonymous memory. /proc/PID/maps acts as a thread group level view, where all thread stack vmas are marked as [stack:TID] where TID is the process ID of the task that uses that vma as stack, while the process stack is marked as [stack]. So /proc/PID/maps will look like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Thus marking all vmas that are used as stacks by the threads in the thread group along with the process stack. The task level maps will however like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] where only the vma that is being used as a stack by *that* task is marked as [stack]. Analogous changes have been made to /proc/PID/smaps, /proc/PID/numa_maps, /proc/PID/task/TID/smaps and /proc/PID/task/TID/numa_maps. Relevant snippets from smaps and numa_maps: [siddhesh@localhost ~ ]$ pgrep a.out 1441 [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack" 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack" 7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2 7fff6273a000 default stack anon=3 dirty=3 N0=3 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack" 7f8a44492000 default stack anon=2 dirty=2 N0=2 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack" 7fff6273a000 default stack anon=3 dirty=3 N0=3 [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix build] Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Jamie Lokier <jamie@shareable.org> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:04 +00:00
{
struct task_struct * __maybe_unused t = current;
procfs: mark thread stack correctly in proc/<pid>/maps Stack for a new thread is mapped by userspace code and passed via sys_clone. This memory is currently seen as anonymous in /proc/<pid>/maps, which makes it difficult to ascertain which mappings are being used for thread stacks. This patch uses the individual task stack pointers to determine which vmas are actually thread stacks. For a multithreaded program like the following: #include <pthread.h> void *thread_main(void *foo) { while(1); } int main() { pthread_t t; pthread_create(&t, NULL, thread_main, NULL); pthread_join(t, NULL); } proc/PID/maps looks like the following: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but that is not always a reliable way to find out which vma is a thread stack. Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same content. With this patch in place, /proc/PID/task/TID/maps are treated as 'maps as the task would see it' and hence, only the vma that that task uses as stack is marked as [stack]. All other 'stack' vmas are marked as anonymous memory. /proc/PID/maps acts as a thread group level view, where all thread stack vmas are marked as [stack:TID] where TID is the process ID of the task that uses that vma as stack, while the process stack is marked as [stack]. So /proc/PID/maps will look like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Thus marking all vmas that are used as stacks by the threads in the thread group along with the process stack. The task level maps will however like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] where only the vma that is being used as a stack by *that* task is marked as [stack]. Analogous changes have been made to /proc/PID/smaps, /proc/PID/numa_maps, /proc/PID/task/TID/smaps and /proc/PID/task/TID/numa_maps. Relevant snippets from smaps and numa_maps: [siddhesh@localhost ~ ]$ pgrep a.out 1441 [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack" 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack" 7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2 7fff6273a000 default stack anon=3 dirty=3 N0=3 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack" 7f8a44492000 default stack anon=2 dirty=2 N0=2 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack" 7fff6273a000 default stack anon=3 dirty=3 N0=3 [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix build] Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Jamie Lokier <jamie@shareable.org> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:04 +00:00
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}
/*
* Change backing file, only valid to use during initial VMA setup.
*/
void vma_set_file(struct vm_area_struct *vma, struct file *file)
{
/* Changing an anonymous vma with this is illegal */
get_file(file);
swap(vma->vm_file, file);
fput(file);
}
EXPORT_SYMBOL(vma_set_file);
mm, fs: move randomize_stack_top from fs to mm Patch series "Provide generic top-down mmap layout functions", v6. This series introduces generic functions to make top-down mmap layout easily accessible to architectures, in particular riscv which was the initial goal of this series. The generic implementation was taken from arm64 and used successively by arm, mips and finally riscv. Note that in addition the series fixes 2 issues: - stack randomization was taken into account even if not necessary. - [1] fixed an issue with mmap base which did not take into account randomization but did not report it to arm and mips, so by moving arm64 into a generic library, this problem is now fixed for both architectures. This work is an effort to factorize architecture functions to avoid code duplication and oversights as in [1]. [1]: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1429066.html This patch (of 14): This preparatory commit moves this function so that further introduction of generic topdown mmap layout is contained only in mm/util.c. Link: http://lkml.kernel.org/r/20190730055113.23635-2-alex@ghiti.fr Signed-off-by: Alexandre Ghiti <alex@ghiti.fr> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Burton <paul.burton@mips.com> Cc: James Hogan <jhogan@kernel.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-23 22:38:37 +00:00
#ifndef STACK_RND_MASK
#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */
#endif
unsigned long randomize_stack_top(unsigned long stack_top)
{
unsigned long random_variable = 0;
if (current->flags & PF_RANDOMIZE) {
random_variable = get_random_long();
random_variable &= STACK_RND_MASK;
random_variable <<= PAGE_SHIFT;
}
#ifdef CONFIG_STACK_GROWSUP
return PAGE_ALIGN(stack_top) + random_variable;
#else
return PAGE_ALIGN(stack_top) - random_variable;
#endif
}
#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
/* Is the current task 32bit ? */
if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task())
return randomize_page(mm->brk, SZ_32M);
return randomize_page(mm->brk, SZ_1G);
}
unsigned long arch_mmap_rnd(void)
{
unsigned long rnd;
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
if (is_compat_task())
rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
else
#endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */
rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
return rnd << PAGE_SHIFT;
}
static int mmap_is_legacy(struct rlimit *rlim_stack)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
if (rlim_stack->rlim_cur == RLIM_INFINITY)
return 1;
return sysctl_legacy_va_layout;
}
/*
* Leave enough space between the mmap area and the stack to honour ulimit in
* the face of randomisation.
*/
#define MIN_GAP (SZ_128M)
#define MAX_GAP (STACK_TOP / 6 * 5)
static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
{
unsigned long gap = rlim_stack->rlim_cur;
unsigned long pad = stack_guard_gap;
/* Account for stack randomization if necessary */
if (current->flags & PF_RANDOMIZE)
pad += (STACK_RND_MASK << PAGE_SHIFT);
/* Values close to RLIM_INFINITY can overflow. */
if (gap + pad > gap)
gap += pad;
if (gap < MIN_GAP)
gap = MIN_GAP;
else if (gap > MAX_GAP)
gap = MAX_GAP;
return PAGE_ALIGN(STACK_TOP - gap - rnd);
}
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
unsigned long random_factor = 0UL;
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
if (mmap_is_legacy(rlim_stack)) {
mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
mm->get_unmapped_area = arch_get_unmapped_area;
} else {
mm->mmap_base = mmap_base(random_factor, rlim_stack);
mm->get_unmapped_area = arch_get_unmapped_area_topdown;
}
}
#elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
exec: pass stack rlimit into mm layout functions Patch series "exec: Pin stack limit during exec". Attempts to solve problems with the stack limit changing during exec continue to be frustrated[1][2]. In addition to the specific issues around the Stack Clash family of flaws, Andy Lutomirski pointed out[3] other places during exec where the stack limit is used and is assumed to be unchanging. Given the many places it gets used and the fact that it can be manipulated/raced via setrlimit() and prlimit(), I think the only way to handle this is to move away from the "current" view of the stack limit and instead attach it to the bprm, and plumb this down into the functions that need to know the stack limits. This series implements the approach. [1] 04e35f4495dd ("exec: avoid RLIMIT_STACK races with prlimit()") [2] 779f4e1c6c7c ("Revert "exec: avoid RLIMIT_STACK races with prlimit()"") [3] to security@kernel.org, "Subject: existing rlimit races?" This patch (of 3): Since it is possible that the stack rlimit can change externally during exec (either via another thread calling setrlimit() or another process calling prlimit()), provide a way to pass the rlimit down into the per-architecture mm layout functions so that the rlimit can stay in the bprm structure instead of sitting in the signal structure until exec is finalized. Link: http://lkml.kernel.org/r/1518638796-20819-2-git-send-email-keescook@chromium.org Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Willy Tarreau <w@1wt.eu> Cc: Hugh Dickins <hughd@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Jason A. Donenfeld" <Jason@zx2c4.com> Cc: Rik van Riel <riel@redhat.com> Cc: Laura Abbott <labbott@redhat.com> Cc: Greg KH <greg@kroah.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ben Hutchings <ben.hutchings@codethink.co.uk> Cc: Brad Spengler <spender@grsecurity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-10 23:34:53 +00:00
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
mm->mmap_base = TASK_UNMAPPED_BASE;
mm->get_unmapped_area = arch_get_unmapped_area;
}
#endif
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-16 23:30:54 +00:00
/**
* __account_locked_vm - account locked pages to an mm's locked_vm
* @mm: mm to account against
* @pages: number of pages to account
* @inc: %true if @pages should be considered positive, %false if not
* @task: task used to check RLIMIT_MEMLOCK
* @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
*
* Assumes @task and @mm are valid (i.e. at least one reference on each), and
* that mmap_lock is held as writer.
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-16 23:30:54 +00:00
*
* Return:
* * 0 on success
* * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
*/
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
struct task_struct *task, bool bypass_rlim)
{
unsigned long locked_vm, limit;
int ret = 0;
mmap_assert_write_locked(mm);
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-16 23:30:54 +00:00
locked_vm = mm->locked_vm;
if (inc) {
if (!bypass_rlim) {
limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
if (locked_vm + pages > limit)
ret = -ENOMEM;
}
if (!ret)
mm->locked_vm = locked_vm + pages;
} else {
WARN_ON_ONCE(pages > locked_vm);
mm->locked_vm = locked_vm - pages;
}
pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid,
(void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT,
locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK),
ret ? " - exceeded" : "");
return ret;
}
EXPORT_SYMBOL_GPL(__account_locked_vm);
/**
* account_locked_vm - account locked pages to an mm's locked_vm
* @mm: mm to account against, may be NULL
* @pages: number of pages to account
* @inc: %true if @pages should be considered positive, %false if not
*
* Assumes a non-NULL @mm is valid (i.e. at least one reference on it).
*
* Return:
* * 0 on success, or if mm is NULL
* * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
*/
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc)
{
int ret;
if (pages == 0 || !mm)
return 0;
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:33:25 +00:00
mmap_write_lock(mm);
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-16 23:30:54 +00:00
ret = __account_locked_vm(mm, pages, inc, current,
capable(CAP_IPC_LOCK));
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:33:25 +00:00
mmap_write_unlock(mm);
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-16 23:30:54 +00:00
return ret;
}
EXPORT_SYMBOL_GPL(account_locked_vm);
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff)
{
unsigned long ret;
struct mm_struct *mm = current->mm;
unsigned long populate;
LIST_HEAD(uf);
ret = security_mmap_file(file, prot, flag);
if (!ret) {
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:33:25 +00:00
if (mmap_write_lock_killable(mm))
return -EINTR;
ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate,
&uf);
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:33:25 +00:00
mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(ret, populate);
}
return ret;
}
unsigned long vm_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long offset)
{
if (unlikely(offset + PAGE_ALIGN(len) < offset))
return -EINVAL;
if (unlikely(offset_in_page(offset)))
return -EINVAL;
return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(vm_mmap);
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:09 +00:00
/**
* kvmalloc_node - attempt to allocate physically contiguous memory, but upon
* failure, fall back to non-contiguous (vmalloc) allocation.
* @size: size of the request.
* @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL.
* @node: numa node to allocate from
*
* Uses kmalloc to get the memory but if the allocation fails then falls back
* to the vmalloc allocator. Use kvfree for freeing the memory.
*
* GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier.
* __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is
* preferable to the vmalloc fallback, due to visible performance drawbacks.
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:09 +00:00
*
* Return: pointer to the allocated memory of %NULL in case of failure
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:09 +00:00
*/
void *kvmalloc_node(size_t size, gfp_t flags, int node)
{
gfp_t kmalloc_flags = flags;
void *ret;
/*
* We want to attempt a large physically contiguous block first because
* it is less likely to fragment multiple larger blocks and therefore
* contribute to a long term fragmentation less than vmalloc fallback.
* However make sure that larger requests are not too disruptive - no
* OOM killer and no allocation failure warnings as we have a fallback.
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:09 +00:00
*/
if (size > PAGE_SIZE) {
kmalloc_flags |= __GFP_NOWARN;
if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL))
kmalloc_flags |= __GFP_NORETRY;
/* nofail semantic is implemented by the vmalloc fallback */
kmalloc_flags &= ~__GFP_NOFAIL;
}
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:09 +00:00
ret = kmalloc_node(size, kmalloc_flags, node);
/*
* It doesn't really make sense to fallback to vmalloc for sub page
* requests
*/
if (ret || size <= PAGE_SIZE)
return ret;
/* Don't even allow crazy sizes */
mm: Consider __GFP_NOWARN flag for oversized kvmalloc() calls syzkaller was recently triggering an oversized kvmalloc() warning via xdp_umem_create(). The triggered warning was added back in 7661809d493b ("mm: don't allow oversized kvmalloc() calls"). The rationale for the warning for huge kvmalloc sizes was as a reaction to a security bug where the size was more than UINT_MAX but not everything was prepared to handle unsigned long sizes. Anyway, the AF_XDP related call trace from this syzkaller report was: kvmalloc include/linux/mm.h:806 [inline] kvmalloc_array include/linux/mm.h:824 [inline] kvcalloc include/linux/mm.h:829 [inline] xdp_umem_pin_pages net/xdp/xdp_umem.c:102 [inline] xdp_umem_reg net/xdp/xdp_umem.c:219 [inline] xdp_umem_create+0x6a5/0xf00 net/xdp/xdp_umem.c:252 xsk_setsockopt+0x604/0x790 net/xdp/xsk.c:1068 __sys_setsockopt+0x1fd/0x4e0 net/socket.c:2176 __do_sys_setsockopt net/socket.c:2187 [inline] __se_sys_setsockopt net/socket.c:2184 [inline] __x64_sys_setsockopt+0xb5/0x150 net/socket.c:2184 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Björn mentioned that requests for >2GB allocation can still be valid: The structure that is being allocated is the page-pinning accounting. AF_XDP has an internal limit of U32_MAX pages, which is *a lot*, but still fewer than what memcg allows (PAGE_COUNTER_MAX is a LONG_MAX/ PAGE_SIZE on 64 bit systems). [...] I could just change from U32_MAX to INT_MAX, but as I stated earlier that has a hacky feeling to it. [...] From my perspective, the code isn't broken, with the memcg limits in consideration. [...] Linus says: [...] Pretty much every time this has come up, the kernel warning has shown that yes, the code was broken and there really wasn't a reason for doing allocations that big. Of course, some people would be perfectly fine with the allocation failing, they just don't want the warning. I didn't want __GFP_NOWARN to shut it up originally because I wanted people to see all those cases, but these days I think we can just say "yeah, people can shut it up explicitly by saying 'go ahead and fail this allocation, don't warn about it'". So enough time has passed that by now I'd certainly be ok with [it]. Thus allow call-sites to silence such userspace triggered splats if the allocation requests have __GFP_NOWARN. For xdp_umem_pin_pages()'s call to kvcalloc() this is already the case, so nothing else needed there. Fixes: 7661809d493b ("mm: don't allow oversized kvmalloc() calls") Reported-by: syzbot+11421fbbff99b989670e@syzkaller.appspotmail.com Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: syzbot+11421fbbff99b989670e@syzkaller.appspotmail.com Cc: Björn Töpel <bjorn@kernel.org> Cc: Magnus Karlsson <magnus.karlsson@intel.com> Cc: Willy Tarreau <w@1wt.eu> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Jakub Kicinski <kuba@kernel.org> Cc: David S. Miller <davem@davemloft.net> Link: https://lore.kernel.org/bpf/CAJ+HfNhyfsT5cS_U9EC213ducHs9k9zNxX9+abqC0kTrPbQ0gg@mail.gmail.com Link: https://lore.kernel.org/bpf/20211201202905.b9892171e3f5b9a60f9da251@linux-foundation.org Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Ackd-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-04 14:26:32 +00:00
if (unlikely(size > INT_MAX)) {
WARN_ON_ONCE(!(flags & __GFP_NOWARN));
return NULL;
mm: Consider __GFP_NOWARN flag for oversized kvmalloc() calls syzkaller was recently triggering an oversized kvmalloc() warning via xdp_umem_create(). The triggered warning was added back in 7661809d493b ("mm: don't allow oversized kvmalloc() calls"). The rationale for the warning for huge kvmalloc sizes was as a reaction to a security bug where the size was more than UINT_MAX but not everything was prepared to handle unsigned long sizes. Anyway, the AF_XDP related call trace from this syzkaller report was: kvmalloc include/linux/mm.h:806 [inline] kvmalloc_array include/linux/mm.h:824 [inline] kvcalloc include/linux/mm.h:829 [inline] xdp_umem_pin_pages net/xdp/xdp_umem.c:102 [inline] xdp_umem_reg net/xdp/xdp_umem.c:219 [inline] xdp_umem_create+0x6a5/0xf00 net/xdp/xdp_umem.c:252 xsk_setsockopt+0x604/0x790 net/xdp/xsk.c:1068 __sys_setsockopt+0x1fd/0x4e0 net/socket.c:2176 __do_sys_setsockopt net/socket.c:2187 [inline] __se_sys_setsockopt net/socket.c:2184 [inline] __x64_sys_setsockopt+0xb5/0x150 net/socket.c:2184 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Björn mentioned that requests for >2GB allocation can still be valid: The structure that is being allocated is the page-pinning accounting. AF_XDP has an internal limit of U32_MAX pages, which is *a lot*, but still fewer than what memcg allows (PAGE_COUNTER_MAX is a LONG_MAX/ PAGE_SIZE on 64 bit systems). [...] I could just change from U32_MAX to INT_MAX, but as I stated earlier that has a hacky feeling to it. [...] From my perspective, the code isn't broken, with the memcg limits in consideration. [...] Linus says: [...] Pretty much every time this has come up, the kernel warning has shown that yes, the code was broken and there really wasn't a reason for doing allocations that big. Of course, some people would be perfectly fine with the allocation failing, they just don't want the warning. I didn't want __GFP_NOWARN to shut it up originally because I wanted people to see all those cases, but these days I think we can just say "yeah, people can shut it up explicitly by saying 'go ahead and fail this allocation, don't warn about it'". So enough time has passed that by now I'd certainly be ok with [it]. Thus allow call-sites to silence such userspace triggered splats if the allocation requests have __GFP_NOWARN. For xdp_umem_pin_pages()'s call to kvcalloc() this is already the case, so nothing else needed there. Fixes: 7661809d493b ("mm: don't allow oversized kvmalloc() calls") Reported-by: syzbot+11421fbbff99b989670e@syzkaller.appspotmail.com Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: syzbot+11421fbbff99b989670e@syzkaller.appspotmail.com Cc: Björn Töpel <bjorn@kernel.org> Cc: Magnus Karlsson <magnus.karlsson@intel.com> Cc: Willy Tarreau <w@1wt.eu> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Jakub Kicinski <kuba@kernel.org> Cc: David S. Miller <davem@davemloft.net> Link: https://lore.kernel.org/bpf/CAJ+HfNhyfsT5cS_U9EC213ducHs9k9zNxX9+abqC0kTrPbQ0gg@mail.gmail.com Link: https://lore.kernel.org/bpf/20211201202905.b9892171e3f5b9a60f9da251@linux-foundation.org Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Ackd-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-04 14:26:32 +00:00
}
mm: remove __vmalloc_node_flags_caller Just use __vmalloc_node instead which gets and extra argument. To be able to to use __vmalloc_node in all caller make it available outside of vmalloc and implement it in nommu.c. [akpm@linux-foundation.org: fix nommu build] Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Airlie <airlied@linux.ie> Cc: Gao Xiang <xiang@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Laura Abbott <labbott@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Kelley <mikelley@microsoft.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Sakari Ailus <sakari.ailus@linux.intel.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Sumit Semwal <sumit.semwal@linaro.org> Cc: Wei Liu <wei.liu@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: http://lkml.kernel.org/r/20200414131348.444715-25-hch@lst.de Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-02 04:51:53 +00:00
return __vmalloc_node(size, 1, flags, node,
mm, vmalloc: fix vmalloc users tracking properly Commit 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") has pulled asm/pgtable.h include dependency to linux/vmalloc.h and that turned out to be a bad idea for some architectures. E.g. m68k fails with In file included from arch/m68k/include/asm/pgtable_mm.h:145:0, from arch/m68k/include/asm/pgtable.h:4, from include/linux/vmalloc.h:9, from arch/m68k/kernel/module.c:9: arch/m68k/include/asm/mcf_pgtable.h: In function 'nocache_page': >> arch/m68k/include/asm/mcf_pgtable.h:339:43: error: 'init_mm' undeclared (first use in this function) #define pgd_offset_k(address) pgd_offset(&init_mm, address) as spotted by kernel build bot. nios2 fails for other reason In file included from include/asm-generic/io.h:767:0, from arch/nios2/include/asm/io.h:61, from include/linux/io.h:25, from arch/nios2/include/asm/pgtable.h:18, from include/linux/mm.h:70, from include/linux/pid_namespace.h:6, from include/linux/ptrace.h:9, from arch/nios2/include/uapi/asm/elf.h:23, from arch/nios2/include/asm/elf.h:22, from include/linux/elf.h:4, from include/linux/module.h:15, from init/main.c:16: include/linux/vmalloc.h: In function '__vmalloc_node_flags': include/linux/vmalloc.h:99:40: error: 'PAGE_KERNEL' undeclared (first use in this function); did you mean 'GFP_KERNEL'? which is due to the newly added #include <asm/pgtable.h>, which on nios2 includes <linux/io.h> and thus <asm/io.h> and <asm-generic/io.h> which again includes <linux/vmalloc.h>. Tweaking that around just turns out a bigger headache than necessary. This patch reverts 1f5307b1e094 and reimplements the original fix in a different way. __vmalloc_node_flags can stay static inline which will cover vmalloc* functions. We only have one external user (kvmalloc_node) and we can export __vmalloc_node_flags_caller and provide the caller directly. This is much simpler and it doesn't really need any games with header files. [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: revert old comment] Link: http://lkml.kernel.org/r/20170509211054.GB16325@dhcp22.suse.cz Fixes: 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") Link: http://lkml.kernel.org/r/20170509153702.GR6481@dhcp22.suse.cz Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-12 22:46:41 +00:00
__builtin_return_address(0));
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:09 +00:00
}
EXPORT_SYMBOL(kvmalloc_node);
/**
* kvfree() - Free memory.
* @addr: Pointer to allocated memory.
*
* kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc().
* It is slightly more efficient to use kfree() or vfree() if you are certain
* that you know which one to use.
*
* Context: Either preemptible task context or not-NMI interrupt.
*/
void kvfree(const void *addr)
{
if (is_vmalloc_addr(addr))
vfree(addr);
else
kfree(addr);
}
EXPORT_SYMBOL(kvfree);
/**
* kvfree_sensitive - Free a data object containing sensitive information.
* @addr: address of the data object to be freed.
* @len: length of the data object.
*
* Use the special memzero_explicit() function to clear the content of a
* kvmalloc'ed object containing sensitive data to make sure that the
* compiler won't optimize out the data clearing.
*/
void kvfree_sensitive(const void *addr, size_t len)
{
if (likely(!ZERO_OR_NULL_PTR(addr))) {
memzero_explicit((void *)addr, len);
kvfree(addr);
}
}
EXPORT_SYMBOL(kvfree_sensitive);
mm: Add kvrealloc() During log recovery of an XFS filesystem with 64kB directory buffers, rebuilding a buffer split across two log records results in a memory allocation warning from krealloc like this: xfs filesystem being mounted at /mnt/scratch supports timestamps until 2038 (0x7fffffff) XFS (dm-0): Unmounting Filesystem XFS (dm-0): Mounting V5 Filesystem XFS (dm-0): Starting recovery (logdev: internal) ------------[ cut here ]------------ WARNING: CPU: 5 PID: 3435170 at mm/page_alloc.c:3539 get_page_from_freelist+0xdee/0xe40 ..... RIP: 0010:get_page_from_freelist+0xdee/0xe40 Call Trace: ? complete+0x3f/0x50 __alloc_pages+0x16f/0x300 alloc_pages+0x87/0x110 kmalloc_order+0x2c/0x90 kmalloc_order_trace+0x1d/0x90 __kmalloc_track_caller+0x215/0x270 ? xlog_recover_add_to_cont_trans+0x63/0x1f0 krealloc+0x54/0xb0 xlog_recover_add_to_cont_trans+0x63/0x1f0 xlog_recovery_process_trans+0xc1/0xd0 xlog_recover_process_ophdr+0x86/0x130 xlog_recover_process_data+0x9f/0x160 xlog_recover_process+0xa2/0x120 xlog_do_recovery_pass+0x40b/0x7d0 ? __irq_work_queue_local+0x4f/0x60 ? irq_work_queue+0x3a/0x50 xlog_do_log_recovery+0x70/0x150 xlog_do_recover+0x38/0x1d0 xlog_recover+0xd8/0x170 xfs_log_mount+0x181/0x300 xfs_mountfs+0x4a1/0x9b0 xfs_fs_fill_super+0x3c0/0x7b0 get_tree_bdev+0x171/0x270 ? suffix_kstrtoint.constprop.0+0xf0/0xf0 xfs_fs_get_tree+0x15/0x20 vfs_get_tree+0x24/0xc0 path_mount+0x2f5/0xaf0 __x64_sys_mount+0x108/0x140 do_syscall_64+0x3a/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae Essentially, we are taking a multi-order allocation from kmem_alloc() (which has an open coded no fail, no warn loop) and then reallocating it out to 64kB using krealloc(__GFP_NOFAIL) and that is then triggering the above warning. This is a regression caused by converting this code from an open coded no fail/no warn reallocation loop to using __GFP_NOFAIL. What we actually need here is kvrealloc(), so that if contiguous page allocation fails we fall back to vmalloc() and we don't get nasty warnings happening in XFS. Fixes: 771915c4f688 ("xfs: remove kmem_realloc()") Signed-off-by: Dave Chinner <dchinner@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-08-09 17:10:00 +00:00
void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
{
void *newp;
if (oldsize >= newsize)
return (void *)p;
newp = kvmalloc(newsize, flags);
if (!newp)
return NULL;
memcpy(newp, p, oldsize);
kvfree(p);
return newp;
}
EXPORT_SYMBOL(kvrealloc);
/**
* __vmalloc_array - allocate memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
void *__vmalloc_array(size_t n, size_t size, gfp_t flags)
{
size_t bytes;
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
return __vmalloc(bytes, flags);
}
EXPORT_SYMBOL(__vmalloc_array);
/**
* vmalloc_array - allocate memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
*/
void *vmalloc_array(size_t n, size_t size)
{
return __vmalloc_array(n, size, GFP_KERNEL);
}
EXPORT_SYMBOL(vmalloc_array);
/**
* __vcalloc - allocate and zero memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
void *__vcalloc(size_t n, size_t size, gfp_t flags)
{
return __vmalloc_array(n, size, flags | __GFP_ZERO);
}
EXPORT_SYMBOL(__vcalloc);
/**
* vcalloc - allocate and zero memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
*/
void *vcalloc(size_t n, size_t size)
{
return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO);
}
EXPORT_SYMBOL(vcalloc);
/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
return folio_raw_mapping(page_folio(page));
}
/**
* folio_mapped - Is this folio mapped into userspace?
* @folio: The folio.
*
* Return: True if any page in this folio is referenced by user page tables.
*/
bool folio_mapped(struct folio *folio)
{
long i, nr;
if (!folio_test_large(folio))
return atomic_read(&folio->_mapcount) >= 0;
if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
return true;
if (folio_test_hugetlb(folio))
return false;
nr = folio_nr_pages(folio);
for (i = 0; i < nr; i++) {
if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0)
return true;
}
return false;
}
EXPORT_SYMBOL(folio_mapped);
struct anon_vma *folio_anon_vma(struct folio *folio)
{
unsigned long mapping = (unsigned long)folio->mapping;
if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
return NULL;
return (void *)(mapping - PAGE_MAPPING_ANON);
}
mm/util: Add folio_mapping() and folio_file_mapping() These are the folio equivalent of page_mapping() and page_file_mapping(). Add an out-of-line page_mapping() wrapper around folio_mapping() in order to prevent the page_folio() call from bloating every caller of page_mapping(). Adjust page_file_mapping() and page_mapping_file() to use folios internally. Rename __page_file_mapping() to swapcache_mapping() and change it to take a folio. This ends up saving 122 bytes of text overall. folio_mapping() is 45 bytes shorter than page_mapping() was, but the new page_mapping() wrapper is 30 bytes. The major reduction is a few bytes less in dozens of nfs functions (which call page_file_mapping()). Most of these appear to be a slight change in gcc's register allocation decisions, which allow: 48 8b 56 08 mov 0x8(%rsi),%rdx 48 8d 42 ff lea -0x1(%rdx),%rax 83 e2 01 and $0x1,%edx 48 0f 44 c6 cmove %rsi,%rax to become: 48 8b 46 08 mov 0x8(%rsi),%rax 48 8d 78 ff lea -0x1(%rax),%rdi a8 01 test $0x1,%al 48 0f 44 fe cmove %rsi,%rdi for a reduction of a single byte. Once the NFS client is converted to use folios, this entire sequence will disappear. Also add folio_mapping() documentation. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Jeff Layton <jlayton@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: William Kucharski <william.kucharski@oracle.com> Reviewed-by: David Howells <dhowells@redhat.com>
2020-12-10 15:55:05 +00:00
/**
* folio_mapping - Find the mapping where this folio is stored.
* @folio: The folio.
*
* For folios which are in the page cache, return the mapping that this
* page belongs to. Folios in the swap cache return the swap mapping
* this page is stored in (which is different from the mapping for the
* swap file or swap device where the data is stored).
*
* You can call this for folios which aren't in the swap cache or page
* cache and it will return NULL.
*/
struct address_space *folio_mapping(struct folio *folio)
{
struct address_space *mapping;
mm: fix crash when using XFS on loopback Commit 8456a648cf44 ("slab: use struct page for slab management") causes a crash in the LVM2 testsuite on PA-RISC (the crashing test is fsadm.sh). The testsuite doesn't crash on 3.12, crashes on 3.13-rc1 and later. Bad Address (null pointer deref?): Code=15 regs=000000413edd89a0 (Addr=000006202224647d) CPU: 3 PID: 24008 Comm: loop0 Not tainted 3.13.0-rc6 #5 task: 00000001bf3c0048 ti: 000000413edd8000 task.ti: 000000413edd8000 YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI PSW: 00001000000001101111100100001110 Not tainted r00-03 000000ff0806f90e 00000000405c8de0 000000004013e6c0 000000413edd83f0 r04-07 00000000405a95e0 0000000000000200 00000001414735f0 00000001bf349e40 r08-11 0000000010fe3d10 0000000000000001 00000040829c7778 000000413efd9000 r12-15 0000000000000000 000000004060d800 0000000010fe3000 0000000010fe3000 r16-19 000000413edd82a0 00000041078ddbc0 0000000000000010 0000000000000001 r20-23 0008f3d0d83a8000 0000000000000000 00000040829c7778 0000000000000080 r24-27 00000001bf349e40 00000001bf349e40 202d66202224640d 00000000405a95e0 r28-31 202d662022246465 000000413edd88f0 000000413edd89a0 0000000000000001 sr00-03 000000000532c000 0000000000000000 0000000000000000 000000000532c000 sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000 IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000401fe42c 00000000401fe430 IIR: 539c0030 ISR: 00000000202d6000 IOR: 000006202224647d CPU: 3 CR30: 000000413edd8000 CR31: 0000000000000000 ORIG_R28: 00000000405a95e0 IAOQ[0]: vma_interval_tree_iter_first+0x14/0x48 IAOQ[1]: vma_interval_tree_iter_first+0x18/0x48 RP(r2): flush_dcache_page+0x128/0x388 Backtrace: flush_dcache_page+0x128/0x388 lo_splice_actor+0x90/0x148 [loop] splice_from_pipe_feed+0xc0/0x1d0 __splice_from_pipe+0xac/0xc0 lo_direct_splice_actor+0x1c/0x70 [loop] splice_direct_to_actor+0xec/0x228 lo_receive+0xe4/0x298 [loop] loop_thread+0x478/0x640 [loop] kthread+0x134/0x168 end_fault_vector+0x20/0x28 xfs_setsize_buftarg+0x0/0x90 [xfs] Kernel panic - not syncing: Bad Address (null pointer deref?) Commit 8456a648cf44 changes the page structure so that the slab subsystem reuses the page->mapping field. The crash happens in the following way: * XFS allocates some memory from slab and issues a bio to read data into it. * the bio is sent to the loopback device. * lo_receive creates an actor and calls splice_direct_to_actor. * lo_splice_actor copies data to the target page. * lo_splice_actor calls flush_dcache_page because the page may be mapped by userspace. In that case we need to flush the kernel cache. * flush_dcache_page asks for the list of userspace mappings, however that page->mapping field is reused by the slab subsystem for a different purpose. This causes the crash. Note that other architectures without coherent caches (sparc, arm, mips) also call page_mapping from flush_dcache_page, so they may crash in the same way. This patch fixes this bug by testing if the page is a slab page in page_mapping and returning NULL if it is. The patch also fixes VM_BUG_ON(PageSlab(page)) that could happen in earlier kernels in the same scenario on architectures without cache coherence when CONFIG_DEBUG_VM is enabled - so it should be backported to stable kernels. In the old kernels, the function page_mapping is placed in include/linux/mm.h, so you should modify the patch accordingly when backporting it. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: John David Anglin <dave.anglin@bell.net>] Cc: Andi Kleen <ak@linux.intel.com> Cc: Christoph Lameter <cl@linux.com> Acked-by: Pekka Enberg <penberg@kernel.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Helge Deller <deller@gmx.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-15 01:56:40 +00:00
/* This happens if someone calls flush_dcache_page on slab page */
mm/util: Add folio_mapping() and folio_file_mapping() These are the folio equivalent of page_mapping() and page_file_mapping(). Add an out-of-line page_mapping() wrapper around folio_mapping() in order to prevent the page_folio() call from bloating every caller of page_mapping(). Adjust page_file_mapping() and page_mapping_file() to use folios internally. Rename __page_file_mapping() to swapcache_mapping() and change it to take a folio. This ends up saving 122 bytes of text overall. folio_mapping() is 45 bytes shorter than page_mapping() was, but the new page_mapping() wrapper is 30 bytes. The major reduction is a few bytes less in dozens of nfs functions (which call page_file_mapping()). Most of these appear to be a slight change in gcc's register allocation decisions, which allow: 48 8b 56 08 mov 0x8(%rsi),%rdx 48 8d 42 ff lea -0x1(%rdx),%rax 83 e2 01 and $0x1,%edx 48 0f 44 c6 cmove %rsi,%rax to become: 48 8b 46 08 mov 0x8(%rsi),%rax 48 8d 78 ff lea -0x1(%rax),%rdi a8 01 test $0x1,%al 48 0f 44 fe cmove %rsi,%rdi for a reduction of a single byte. Once the NFS client is converted to use folios, this entire sequence will disappear. Also add folio_mapping() documentation. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Jeff Layton <jlayton@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: William Kucharski <william.kucharski@oracle.com> Reviewed-by: David Howells <dhowells@redhat.com>
2020-12-10 15:55:05 +00:00
if (unlikely(folio_test_slab(folio)))
mm: fix crash when using XFS on loopback Commit 8456a648cf44 ("slab: use struct page for slab management") causes a crash in the LVM2 testsuite on PA-RISC (the crashing test is fsadm.sh). The testsuite doesn't crash on 3.12, crashes on 3.13-rc1 and later. Bad Address (null pointer deref?): Code=15 regs=000000413edd89a0 (Addr=000006202224647d) CPU: 3 PID: 24008 Comm: loop0 Not tainted 3.13.0-rc6 #5 task: 00000001bf3c0048 ti: 000000413edd8000 task.ti: 000000413edd8000 YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI PSW: 00001000000001101111100100001110 Not tainted r00-03 000000ff0806f90e 00000000405c8de0 000000004013e6c0 000000413edd83f0 r04-07 00000000405a95e0 0000000000000200 00000001414735f0 00000001bf349e40 r08-11 0000000010fe3d10 0000000000000001 00000040829c7778 000000413efd9000 r12-15 0000000000000000 000000004060d800 0000000010fe3000 0000000010fe3000 r16-19 000000413edd82a0 00000041078ddbc0 0000000000000010 0000000000000001 r20-23 0008f3d0d83a8000 0000000000000000 00000040829c7778 0000000000000080 r24-27 00000001bf349e40 00000001bf349e40 202d66202224640d 00000000405a95e0 r28-31 202d662022246465 000000413edd88f0 000000413edd89a0 0000000000000001 sr00-03 000000000532c000 0000000000000000 0000000000000000 000000000532c000 sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000 IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000401fe42c 00000000401fe430 IIR: 539c0030 ISR: 00000000202d6000 IOR: 000006202224647d CPU: 3 CR30: 000000413edd8000 CR31: 0000000000000000 ORIG_R28: 00000000405a95e0 IAOQ[0]: vma_interval_tree_iter_first+0x14/0x48 IAOQ[1]: vma_interval_tree_iter_first+0x18/0x48 RP(r2): flush_dcache_page+0x128/0x388 Backtrace: flush_dcache_page+0x128/0x388 lo_splice_actor+0x90/0x148 [loop] splice_from_pipe_feed+0xc0/0x1d0 __splice_from_pipe+0xac/0xc0 lo_direct_splice_actor+0x1c/0x70 [loop] splice_direct_to_actor+0xec/0x228 lo_receive+0xe4/0x298 [loop] loop_thread+0x478/0x640 [loop] kthread+0x134/0x168 end_fault_vector+0x20/0x28 xfs_setsize_buftarg+0x0/0x90 [xfs] Kernel panic - not syncing: Bad Address (null pointer deref?) Commit 8456a648cf44 changes the page structure so that the slab subsystem reuses the page->mapping field. The crash happens in the following way: * XFS allocates some memory from slab and issues a bio to read data into it. * the bio is sent to the loopback device. * lo_receive creates an actor and calls splice_direct_to_actor. * lo_splice_actor copies data to the target page. * lo_splice_actor calls flush_dcache_page because the page may be mapped by userspace. In that case we need to flush the kernel cache. * flush_dcache_page asks for the list of userspace mappings, however that page->mapping field is reused by the slab subsystem for a different purpose. This causes the crash. Note that other architectures without coherent caches (sparc, arm, mips) also call page_mapping from flush_dcache_page, so they may crash in the same way. This patch fixes this bug by testing if the page is a slab page in page_mapping and returning NULL if it is. The patch also fixes VM_BUG_ON(PageSlab(page)) that could happen in earlier kernels in the same scenario on architectures without cache coherence when CONFIG_DEBUG_VM is enabled - so it should be backported to stable kernels. In the old kernels, the function page_mapping is placed in include/linux/mm.h, so you should modify the patch accordingly when backporting it. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: John David Anglin <dave.anglin@bell.net>] Cc: Andi Kleen <ak@linux.intel.com> Cc: Christoph Lameter <cl@linux.com> Acked-by: Pekka Enberg <penberg@kernel.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Helge Deller <deller@gmx.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-15 01:56:40 +00:00
return NULL;
mm/util: Add folio_mapping() and folio_file_mapping() These are the folio equivalent of page_mapping() and page_file_mapping(). Add an out-of-line page_mapping() wrapper around folio_mapping() in order to prevent the page_folio() call from bloating every caller of page_mapping(). Adjust page_file_mapping() and page_mapping_file() to use folios internally. Rename __page_file_mapping() to swapcache_mapping() and change it to take a folio. This ends up saving 122 bytes of text overall. folio_mapping() is 45 bytes shorter than page_mapping() was, but the new page_mapping() wrapper is 30 bytes. The major reduction is a few bytes less in dozens of nfs functions (which call page_file_mapping()). Most of these appear to be a slight change in gcc's register allocation decisions, which allow: 48 8b 56 08 mov 0x8(%rsi),%rdx 48 8d 42 ff lea -0x1(%rdx),%rax 83 e2 01 and $0x1,%edx 48 0f 44 c6 cmove %rsi,%rax to become: 48 8b 46 08 mov 0x8(%rsi),%rax 48 8d 78 ff lea -0x1(%rax),%rdi a8 01 test $0x1,%al 48 0f 44 fe cmove %rsi,%rdi for a reduction of a single byte. Once the NFS client is converted to use folios, this entire sequence will disappear. Also add folio_mapping() documentation. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Jeff Layton <jlayton@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: William Kucharski <william.kucharski@oracle.com> Reviewed-by: David Howells <dhowells@redhat.com>
2020-12-10 15:55:05 +00:00
if (unlikely(folio_test_swapcache(folio)))
return swap_address_space(folio_swap_entry(folio));
mm/util: Add folio_mapping() and folio_file_mapping() These are the folio equivalent of page_mapping() and page_file_mapping(). Add an out-of-line page_mapping() wrapper around folio_mapping() in order to prevent the page_folio() call from bloating every caller of page_mapping(). Adjust page_file_mapping() and page_mapping_file() to use folios internally. Rename __page_file_mapping() to swapcache_mapping() and change it to take a folio. This ends up saving 122 bytes of text overall. folio_mapping() is 45 bytes shorter than page_mapping() was, but the new page_mapping() wrapper is 30 bytes. The major reduction is a few bytes less in dozens of nfs functions (which call page_file_mapping()). Most of these appear to be a slight change in gcc's register allocation decisions, which allow: 48 8b 56 08 mov 0x8(%rsi),%rdx 48 8d 42 ff lea -0x1(%rdx),%rax 83 e2 01 and $0x1,%edx 48 0f 44 c6 cmove %rsi,%rax to become: 48 8b 46 08 mov 0x8(%rsi),%rax 48 8d 78 ff lea -0x1(%rax),%rdi a8 01 test $0x1,%al 48 0f 44 fe cmove %rsi,%rdi for a reduction of a single byte. Once the NFS client is converted to use folios, this entire sequence will disappear. Also add folio_mapping() documentation. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Jeff Layton <jlayton@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: William Kucharski <william.kucharski@oracle.com> Reviewed-by: David Howells <dhowells@redhat.com>
2020-12-10 15:55:05 +00:00
mapping = folio->mapping;
mm: migrate: support non-lru movable page migration We have allowed migration for only LRU pages until now and it was enough to make high-order pages. But recently, embedded system(e.g., webOS, android) uses lots of non-movable pages(e.g., zram, GPU memory) so we have seen several reports about troubles of small high-order allocation. For fixing the problem, there were several efforts (e,g,. enhance compaction algorithm, SLUB fallback to 0-order page, reserved memory, vmalloc and so on) but if there are lots of non-movable pages in system, their solutions are void in the long run. So, this patch is to support facility to change non-movable pages with movable. For the feature, this patch introduces functions related to migration to address_space_operations as well as some page flags. If a driver want to make own pages movable, it should define three functions which are function pointers of struct address_space_operations. 1. bool (*isolate_page) (struct page *page, isolate_mode_t mode); What VM expects on isolate_page function of driver is to return *true* if driver isolates page successfully. On returing true, VM marks the page as PG_isolated so concurrent isolation in several CPUs skip the page for isolation. If a driver cannot isolate the page, it should return *false*. Once page is successfully isolated, VM uses page.lru fields so driver shouldn't expect to preserve values in that fields. 2. int (*migratepage) (struct address_space *mapping, struct page *newpage, struct page *oldpage, enum migrate_mode); After isolation, VM calls migratepage of driver with isolated page. The function of migratepage is to move content of the old page to new page and set up fields of struct page newpage. Keep in mind that you should indicate to the VM the oldpage is no longer movable via __ClearPageMovable() under page_lock if you migrated the oldpage successfully and returns 0. If driver cannot migrate the page at the moment, driver can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time because VM interprets -EAGAIN as "temporal migration failure". On returning any error except -EAGAIN, VM will give up the page migration without retrying in this time. Driver shouldn't touch page.lru field VM using in the functions. 3. void (*putback_page)(struct page *); If migration fails on isolated page, VM should return the isolated page to the driver so VM calls driver's putback_page with migration failed page. In this function, driver should put the isolated page back to the own data structure. 4. non-lru movable page flags There are two page flags for supporting non-lru movable page. * PG_movable Driver should use the below function to make page movable under page_lock. void __SetPageMovable(struct page *page, struct address_space *mapping) It needs argument of address_space for registering migration family functions which will be called by VM. Exactly speaking, PG_movable is not a real flag of struct page. Rather than, VM reuses page->mapping's lower bits to represent it. #define PAGE_MAPPING_MOVABLE 0x2 page->mapping = page->mapping | PAGE_MAPPING_MOVABLE; so driver shouldn't access page->mapping directly. Instead, driver should use page_mapping which mask off the low two bits of page->mapping so it can get right struct address_space. For testing of non-lru movable page, VM supports __PageMovable function. However, it doesn't guarantee to identify non-lru movable page because page->mapping field is unified with other variables in struct page. As well, if driver releases the page after isolation by VM, page->mapping doesn't have stable value although it has PAGE_MAPPING_MOVABLE (Look at __ClearPageMovable). But __PageMovable is cheap to catch whether page is LRU or non-lru movable once the page has been isolated. Because LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also good for just peeking to test non-lru movable pages before more expensive checking with lock_page in pfn scanning to select victim. For guaranteeing non-lru movable page, VM provides PageMovable function. Unlike __PageMovable, PageMovable functions validates page->mapping and mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden destroying of page->mapping. Driver using __SetPageMovable should clear the flag via __ClearMovablePage under page_lock before the releasing the page. * PG_isolated To prevent concurrent isolation among several CPUs, VM marks isolated page as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru movable page, it can skip it. Driver doesn't need to manipulate the flag because VM will set/clear it automatically. Keep in mind that if driver sees PG_isolated page, it means the page have been isolated by VM so it shouldn't touch page.lru field. PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag for own purpose. [opensource.ganesh@gmail.com: mm/compaction: remove local variable is_lru] Link: http://lkml.kernel.org/r/20160618014841.GA7422@leo-test Link: http://lkml.kernel.org/r/1464736881-24886-3-git-send-email-minchan@kernel.org Signed-off-by: Gioh Kim <gi-oh.kim@profitbricks.com> Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Ganesh Mahendran <opensource.ganesh@gmail.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: John Einar Reitan <john.reitan@foss.arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-26 22:23:05 +00:00
if ((unsigned long)mapping & PAGE_MAPPING_ANON)
return NULL;
mm: migrate: support non-lru movable page migration We have allowed migration for only LRU pages until now and it was enough to make high-order pages. But recently, embedded system(e.g., webOS, android) uses lots of non-movable pages(e.g., zram, GPU memory) so we have seen several reports about troubles of small high-order allocation. For fixing the problem, there were several efforts (e,g,. enhance compaction algorithm, SLUB fallback to 0-order page, reserved memory, vmalloc and so on) but if there are lots of non-movable pages in system, their solutions are void in the long run. So, this patch is to support facility to change non-movable pages with movable. For the feature, this patch introduces functions related to migration to address_space_operations as well as some page flags. If a driver want to make own pages movable, it should define three functions which are function pointers of struct address_space_operations. 1. bool (*isolate_page) (struct page *page, isolate_mode_t mode); What VM expects on isolate_page function of driver is to return *true* if driver isolates page successfully. On returing true, VM marks the page as PG_isolated so concurrent isolation in several CPUs skip the page for isolation. If a driver cannot isolate the page, it should return *false*. Once page is successfully isolated, VM uses page.lru fields so driver shouldn't expect to preserve values in that fields. 2. int (*migratepage) (struct address_space *mapping, struct page *newpage, struct page *oldpage, enum migrate_mode); After isolation, VM calls migratepage of driver with isolated page. The function of migratepage is to move content of the old page to new page and set up fields of struct page newpage. Keep in mind that you should indicate to the VM the oldpage is no longer movable via __ClearPageMovable() under page_lock if you migrated the oldpage successfully and returns 0. If driver cannot migrate the page at the moment, driver can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time because VM interprets -EAGAIN as "temporal migration failure". On returning any error except -EAGAIN, VM will give up the page migration without retrying in this time. Driver shouldn't touch page.lru field VM using in the functions. 3. void (*putback_page)(struct page *); If migration fails on isolated page, VM should return the isolated page to the driver so VM calls driver's putback_page with migration failed page. In this function, driver should put the isolated page back to the own data structure. 4. non-lru movable page flags There are two page flags for supporting non-lru movable page. * PG_movable Driver should use the below function to make page movable under page_lock. void __SetPageMovable(struct page *page, struct address_space *mapping) It needs argument of address_space for registering migration family functions which will be called by VM. Exactly speaking, PG_movable is not a real flag of struct page. Rather than, VM reuses page->mapping's lower bits to represent it. #define PAGE_MAPPING_MOVABLE 0x2 page->mapping = page->mapping | PAGE_MAPPING_MOVABLE; so driver shouldn't access page->mapping directly. Instead, driver should use page_mapping which mask off the low two bits of page->mapping so it can get right struct address_space. For testing of non-lru movable page, VM supports __PageMovable function. However, it doesn't guarantee to identify non-lru movable page because page->mapping field is unified with other variables in struct page. As well, if driver releases the page after isolation by VM, page->mapping doesn't have stable value although it has PAGE_MAPPING_MOVABLE (Look at __ClearPageMovable). But __PageMovable is cheap to catch whether page is LRU or non-lru movable once the page has been isolated. Because LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also good for just peeking to test non-lru movable pages before more expensive checking with lock_page in pfn scanning to select victim. For guaranteeing non-lru movable page, VM provides PageMovable function. Unlike __PageMovable, PageMovable functions validates page->mapping and mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden destroying of page->mapping. Driver using __SetPageMovable should clear the flag via __ClearMovablePage under page_lock before the releasing the page. * PG_isolated To prevent concurrent isolation among several CPUs, VM marks isolated page as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru movable page, it can skip it. Driver doesn't need to manipulate the flag because VM will set/clear it automatically. Keep in mind that if driver sees PG_isolated page, it means the page have been isolated by VM so it shouldn't touch page.lru field. PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag for own purpose. [opensource.ganesh@gmail.com: mm/compaction: remove local variable is_lru] Link: http://lkml.kernel.org/r/20160618014841.GA7422@leo-test Link: http://lkml.kernel.org/r/1464736881-24886-3-git-send-email-minchan@kernel.org Signed-off-by: Gioh Kim <gi-oh.kim@profitbricks.com> Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Ganesh Mahendran <opensource.ganesh@gmail.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: John Einar Reitan <john.reitan@foss.arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-26 22:23:05 +00:00
return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS);
}
mm/util: Add folio_mapping() and folio_file_mapping() These are the folio equivalent of page_mapping() and page_file_mapping(). Add an out-of-line page_mapping() wrapper around folio_mapping() in order to prevent the page_folio() call from bloating every caller of page_mapping(). Adjust page_file_mapping() and page_mapping_file() to use folios internally. Rename __page_file_mapping() to swapcache_mapping() and change it to take a folio. This ends up saving 122 bytes of text overall. folio_mapping() is 45 bytes shorter than page_mapping() was, but the new page_mapping() wrapper is 30 bytes. The major reduction is a few bytes less in dozens of nfs functions (which call page_file_mapping()). Most of these appear to be a slight change in gcc's register allocation decisions, which allow: 48 8b 56 08 mov 0x8(%rsi),%rdx 48 8d 42 ff lea -0x1(%rdx),%rax 83 e2 01 and $0x1,%edx 48 0f 44 c6 cmove %rsi,%rax to become: 48 8b 46 08 mov 0x8(%rsi),%rax 48 8d 78 ff lea -0x1(%rax),%rdi a8 01 test $0x1,%al 48 0f 44 fe cmove %rsi,%rdi for a reduction of a single byte. Once the NFS client is converted to use folios, this entire sequence will disappear. Also add folio_mapping() documentation. Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Jeff Layton <jlayton@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: William Kucharski <william.kucharski@oracle.com> Reviewed-by: David Howells <dhowells@redhat.com>
2020-12-10 15:55:05 +00:00
EXPORT_SYMBOL(folio_mapping);
/* Slow path of page_mapcount() for compound pages */
int __page_mapcount(struct page *page)
{
int ret;
ret = atomic_read(&page->_mapcount) + 1;
/*
* For file THP page->_mapcount contains total number of mapping
* of the page: no need to look into compound_mapcount.
*/
if (!PageAnon(page) && !PageHuge(page))
return ret;
page = compound_head(page);
ret += atomic_read(compound_mapcount_ptr(page)) + 1;
if (PageDoubleMap(page))
ret--;
return ret;
}
EXPORT_SYMBOL_GPL(__page_mapcount);
/**
* folio_mapcount() - Calculate the number of mappings of this folio.
* @folio: The folio.
*
* A large folio tracks both how many times the entire folio is mapped,
* and how many times each individual page in the folio is mapped.
* This function calculates the total number of times the folio is
* mapped.
*
* Return: The number of times this folio is mapped.
*/
int folio_mapcount(struct folio *folio)
{
int i, compound, nr, ret;
if (likely(!folio_test_large(folio)))
return atomic_read(&folio->_mapcount) + 1;
compound = folio_entire_mapcount(folio);
nr = folio_nr_pages(folio);
if (folio_test_hugetlb(folio))
return compound;
ret = compound;
for (i = 0; i < nr; i++)
ret += atomic_read(&folio_page(folio, i)->_mapcount) + 1;
/* File pages has compound_mapcount included in _mapcount */
if (!folio_test_anon(folio))
return ret - compound * nr;
if (folio_test_double_map(folio))
ret -= nr;
return ret;
}
/**
* folio_copy - Copy the contents of one folio to another.
* @dst: Folio to copy to.
* @src: Folio to copy from.
*
* The bytes in the folio represented by @src are copied to @dst.
* Assumes the caller has validated that @dst is at least as large as @src.
* Can be called in atomic context for order-0 folios, but if the folio is
* larger, it may sleep.
*/
void folio_copy(struct folio *dst, struct folio *src)
{
long i = 0;
long nr = folio_nr_pages(src);
for (;;) {
copy_highpage(folio_page(dst, i), folio_page(src, i));
if (++i == nr)
break;
cond_resched();
}
}
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
int sysctl_overcommit_ratio __read_mostly = 50;
unsigned long sysctl_overcommit_kbytes __read_mostly;
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
sysctl_overcommit_kbytes = 0;
return ret;
}
mm: adjust vm_committed_as_batch according to vm overcommit policy When checking a performance change for will-it-scale scalability mmap test [1], we found very high lock contention for spinlock of percpu counter 'vm_committed_as': 94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave 48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap; 45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap; Actually this heavy lock contention is not always necessary. The 'vm_committed_as' needs to be very precise when the strict OVERCOMMIT_NEVER policy is set, which requires a rather small batch number for the percpu counter. So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies. Also add a sysctl handler to adjust it when the policy is reconfigured. Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. We tested with test platforms in 0day (server, desktop and laptop), and 80%+ platforms shows improvements with that test. And whether it shows improvements depends on if the test mmap size is bigger than the batch number computed. And if the lift is 16X, 1/3 of the platforms will show improvements, though it should help the mmap/unmap usage generally, as Michal Hocko mentioned: : I believe that there are non-synthetic worklaods which would benefit from : a larger batch. E.g. large in memory databases which do large mmaps : during startups from multiple threads. [1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/ Signed-off-by: Feng Tang <feng.tang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Qian Cai <cai@lca.pw> Cc: Kees Cook <keescook@chromium.org> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: kernel test robot <rong.a.chen@intel.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:23:15 +00:00
static void sync_overcommit_as(struct work_struct *dummy)
{
percpu_counter_sync(&vm_committed_as);
}
int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
int new_policy = -1;
mm: adjust vm_committed_as_batch according to vm overcommit policy When checking a performance change for will-it-scale scalability mmap test [1], we found very high lock contention for spinlock of percpu counter 'vm_committed_as': 94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave 48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap; 45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap; Actually this heavy lock contention is not always necessary. The 'vm_committed_as' needs to be very precise when the strict OVERCOMMIT_NEVER policy is set, which requires a rather small batch number for the percpu counter. So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies. Also add a sysctl handler to adjust it when the policy is reconfigured. Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. We tested with test platforms in 0day (server, desktop and laptop), and 80%+ platforms shows improvements with that test. And whether it shows improvements depends on if the test mmap size is bigger than the batch number computed. And if the lift is 16X, 1/3 of the platforms will show improvements, though it should help the mmap/unmap usage generally, as Michal Hocko mentioned: : I believe that there are non-synthetic worklaods which would benefit from : a larger batch. E.g. large in memory databases which do large mmaps : during startups from multiple threads. [1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/ Signed-off-by: Feng Tang <feng.tang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Qian Cai <cai@lca.pw> Cc: Kees Cook <keescook@chromium.org> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: kernel test robot <rong.a.chen@intel.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:23:15 +00:00
int ret;
/*
* The deviation of sync_overcommit_as could be big with loose policy
* like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
* strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
* with the strict "NEVER", and to avoid possible race condition (even
mm: adjust vm_committed_as_batch according to vm overcommit policy When checking a performance change for will-it-scale scalability mmap test [1], we found very high lock contention for spinlock of percpu counter 'vm_committed_as': 94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave 48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap; 45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap; Actually this heavy lock contention is not always necessary. The 'vm_committed_as' needs to be very precise when the strict OVERCOMMIT_NEVER policy is set, which requires a rather small batch number for the percpu counter. So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies. Also add a sysctl handler to adjust it when the policy is reconfigured. Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. We tested with test platforms in 0day (server, desktop and laptop), and 80%+ platforms shows improvements with that test. And whether it shows improvements depends on if the test mmap size is bigger than the batch number computed. And if the lift is 16X, 1/3 of the platforms will show improvements, though it should help the mmap/unmap usage generally, as Michal Hocko mentioned: : I believe that there are non-synthetic worklaods which would benefit from : a larger batch. E.g. large in memory databases which do large mmaps : during startups from multiple threads. [1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/ Signed-off-by: Feng Tang <feng.tang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Qian Cai <cai@lca.pw> Cc: Kees Cook <keescook@chromium.org> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: kernel test robot <rong.a.chen@intel.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:23:15 +00:00
* though user usually won't too frequently do the switching to policy
* OVERCOMMIT_NEVER), the switch is done in the following order:
* 1. changing the batch
* 2. sync percpu count on each CPU
* 3. switch the policy
*/
if (write) {
t = *table;
t.data = &new_policy;
ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
if (ret || new_policy == -1)
mm: adjust vm_committed_as_batch according to vm overcommit policy When checking a performance change for will-it-scale scalability mmap test [1], we found very high lock contention for spinlock of percpu counter 'vm_committed_as': 94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave 48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap; 45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap; Actually this heavy lock contention is not always necessary. The 'vm_committed_as' needs to be very precise when the strict OVERCOMMIT_NEVER policy is set, which requires a rather small batch number for the percpu counter. So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies. Also add a sysctl handler to adjust it when the policy is reconfigured. Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. We tested with test platforms in 0day (server, desktop and laptop), and 80%+ platforms shows improvements with that test. And whether it shows improvements depends on if the test mmap size is bigger than the batch number computed. And if the lift is 16X, 1/3 of the platforms will show improvements, though it should help the mmap/unmap usage generally, as Michal Hocko mentioned: : I believe that there are non-synthetic worklaods which would benefit from : a larger batch. E.g. large in memory databases which do large mmaps : during startups from multiple threads. [1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/ Signed-off-by: Feng Tang <feng.tang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Qian Cai <cai@lca.pw> Cc: Kees Cook <keescook@chromium.org> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: kernel test robot <rong.a.chen@intel.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:23:15 +00:00
return ret;
mm_compute_batch(new_policy);
if (new_policy == OVERCOMMIT_NEVER)
schedule_on_each_cpu(sync_overcommit_as);
sysctl_overcommit_memory = new_policy;
} else {
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
return ret;
}
int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
sysctl_overcommit_ratio = 0;
return ret;
}
/*
* Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
*/
unsigned long vm_commit_limit(void)
{
unsigned long allowed;
if (sysctl_overcommit_kbytes)
allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
else
allowed = ((totalram_pages() - hugetlb_total_pages())
* sysctl_overcommit_ratio / 100);
allowed += total_swap_pages;
return allowed;
}
/*
* Make sure vm_committed_as in one cacheline and not cacheline shared with
* other variables. It can be updated by several CPUs frequently.
*/
struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
/*
* The global memory commitment made in the system can be a metric
* that can be used to drive ballooning decisions when Linux is hosted
* as a guest. On Hyper-V, the host implements a policy engine for dynamically
* balancing memory across competing virtual machines that are hosted.
* Several metrics drive this policy engine including the guest reported
* memory commitment.
mm/util.c: make vm_memory_committed() more accurate percpu_counter_sum_positive() will provide more accurate info. As with percpu_counter_read_positive(), in worst case the deviation could be 'batch * nr_cpus', which is totalram_pages/256 for now, and will be more when the batch gets enlarged. Its time cost is about 800 nanoseconds on a 2C/4T platform and 2~3 microseconds on a 2S/36C/72T Skylake server in normal case, and in worst case where vm_committed_as's spinlock is under severe contention, it costs 30~40 microseconds for the 2S/36C/72T Skylake sever, which should be fine for its only two users: /proc/meminfo and HyperV balloon driver's status trace per second. Signed-off-by: Feng Tang <feng.tang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> # for /proc/meminfo Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Qian Cai <cai@lca.pw> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: kernel test robot <rong.a.chen@intel.com> Cc: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/1592725000-73486-3-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-3-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:23:07 +00:00
*
* The time cost of this is very low for small platforms, and for big
* platform like a 2S/36C/72T Skylake server, in worst case where
* vm_committed_as's spinlock is under severe contention, the time cost
* could be about 30~40 microseconds.
*/
unsigned long vm_memory_committed(void)
{
mm/util.c: make vm_memory_committed() more accurate percpu_counter_sum_positive() will provide more accurate info. As with percpu_counter_read_positive(), in worst case the deviation could be 'batch * nr_cpus', which is totalram_pages/256 for now, and will be more when the batch gets enlarged. Its time cost is about 800 nanoseconds on a 2C/4T platform and 2~3 microseconds on a 2S/36C/72T Skylake server in normal case, and in worst case where vm_committed_as's spinlock is under severe contention, it costs 30~40 microseconds for the 2S/36C/72T Skylake sever, which should be fine for its only two users: /proc/meminfo and HyperV balloon driver's status trace per second. Signed-off-by: Feng Tang <feng.tang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> # for /proc/meminfo Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Qian Cai <cai@lca.pw> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: kernel test robot <rong.a.chen@intel.com> Cc: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/1592725000-73486-3-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-3-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:23:07 +00:00
return percpu_counter_sum_positive(&vm_committed_as);
}
EXPORT_SYMBOL_GPL(vm_memory_committed);
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
* succeed and -ENOMEM implies there is not.
*
* We currently support three overcommit policies, which are set via the
* vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst
*
* Strict overcommit modes added 2002 Feb 26 by Alan Cox.
* Additional code 2002 Jul 20 by Robert Love.
*
* cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
*
* Note this is a helper function intended to be used by LSMs which
* wish to use this logic.
*/
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
mm: fix false-positive OVERCOMMIT_GUESS failures With the default overcommit==guess we occasionally run into mmap rejections despite plenty of memory that would get dropped under pressure but just isn't accounted reclaimable. One example of this is dying cgroups pinned by some page cache. A previous case was auxiliary path name memory associated with dentries; we have since annotated those allocations to avoid overcommit failures (see d79f7aa496fc ("mm: treat indirectly reclaimable memory as free in overcommit logic")). But trying to classify all allocated memory reliably as reclaimable and unreclaimable is a bit of a fool's errand. There could be a myriad of dependencies that constantly change with kernel versions. It becomes even more questionable of an effort when considering how this estimate of available memory is used: it's not compared to the system-wide allocated virtual memory in any way. It's not even compared to the allocating process's address space. It's compared to the single allocation request at hand! So we have an elaborate left-hand side of the equation that tries to assess the exact breathing room the system has available down to a page - and then compare it to an isolated allocation request with no additional context. We could fail an allocation of N bytes, but for two allocations of N/2 bytes we'd do this elaborate dance twice in a row and then still let N bytes of virtual memory through. This doesn't make a whole lot of sense. Let's take a step back and look at the actual goal of the heuristic. From the documentation: Heuristic overcommit handling. Obvious overcommits of address space are refused. Used for a typical system. It ensures a seriously wild allocation fails while allowing overcommit to reduce swap usage. root is allowed to allocate slightly more memory in this mode. This is the default. If all we want to do is catch clearly bogus allocation requests irrespective of the general virtual memory situation, the physical memory counter-part doesn't need to be that complicated, either. When in GUESS mode, catch wild allocations by comparing their request size to total amount of ram and swap in the system. Link: http://lkml.kernel.org/r/20190412191418.26333-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:21:50 +00:00
long allowed;
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
mm: fix false-positive OVERCOMMIT_GUESS failures With the default overcommit==guess we occasionally run into mmap rejections despite plenty of memory that would get dropped under pressure but just isn't accounted reclaimable. One example of this is dying cgroups pinned by some page cache. A previous case was auxiliary path name memory associated with dentries; we have since annotated those allocations to avoid overcommit failures (see d79f7aa496fc ("mm: treat indirectly reclaimable memory as free in overcommit logic")). But trying to classify all allocated memory reliably as reclaimable and unreclaimable is a bit of a fool's errand. There could be a myriad of dependencies that constantly change with kernel versions. It becomes even more questionable of an effort when considering how this estimate of available memory is used: it's not compared to the system-wide allocated virtual memory in any way. It's not even compared to the allocating process's address space. It's compared to the single allocation request at hand! So we have an elaborate left-hand side of the equation that tries to assess the exact breathing room the system has available down to a page - and then compare it to an isolated allocation request with no additional context. We could fail an allocation of N bytes, but for two allocations of N/2 bytes we'd do this elaborate dance twice in a row and then still let N bytes of virtual memory through. This doesn't make a whole lot of sense. Let's take a step back and look at the actual goal of the heuristic. From the documentation: Heuristic overcommit handling. Obvious overcommits of address space are refused. Used for a typical system. It ensures a seriously wild allocation fails while allowing overcommit to reduce swap usage. root is allowed to allocate slightly more memory in this mode. This is the default. If all we want to do is catch clearly bogus allocation requests irrespective of the general virtual memory situation, the physical memory counter-part doesn't need to be that complicated, either. When in GUESS mode, catch wild allocations by comparing their request size to total amount of ram and swap in the system. Link: http://lkml.kernel.org/r/20190412191418.26333-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:21:50 +00:00
if (pages > totalram_pages() + total_swap_pages)
goto error;
mm: fix false-positive OVERCOMMIT_GUESS failures With the default overcommit==guess we occasionally run into mmap rejections despite plenty of memory that would get dropped under pressure but just isn't accounted reclaimable. One example of this is dying cgroups pinned by some page cache. A previous case was auxiliary path name memory associated with dentries; we have since annotated those allocations to avoid overcommit failures (see d79f7aa496fc ("mm: treat indirectly reclaimable memory as free in overcommit logic")). But trying to classify all allocated memory reliably as reclaimable and unreclaimable is a bit of a fool's errand. There could be a myriad of dependencies that constantly change with kernel versions. It becomes even more questionable of an effort when considering how this estimate of available memory is used: it's not compared to the system-wide allocated virtual memory in any way. It's not even compared to the allocating process's address space. It's compared to the single allocation request at hand! So we have an elaborate left-hand side of the equation that tries to assess the exact breathing room the system has available down to a page - and then compare it to an isolated allocation request with no additional context. We could fail an allocation of N bytes, but for two allocations of N/2 bytes we'd do this elaborate dance twice in a row and then still let N bytes of virtual memory through. This doesn't make a whole lot of sense. Let's take a step back and look at the actual goal of the heuristic. From the documentation: Heuristic overcommit handling. Obvious overcommits of address space are refused. Used for a typical system. It ensures a seriously wild allocation fails while allowing overcommit to reduce swap usage. root is allowed to allocate slightly more memory in this mode. This is the default. If all we want to do is catch clearly bogus allocation requests irrespective of the general virtual memory situation, the physical memory counter-part doesn't need to be that complicated, either. When in GUESS mode, catch wild allocations by comparing their request size to total amount of ram and swap in the system. Link: http://lkml.kernel.org/r/20190412191418.26333-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:21:50 +00:00
return 0;
}
allowed = vm_commit_limit();
/*
* Reserve some for root
*/
if (!cap_sys_admin)
allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
/*
* Don't let a single process grow so big a user can't recover
*/
if (mm) {
mm: fix false-positive OVERCOMMIT_GUESS failures With the default overcommit==guess we occasionally run into mmap rejections despite plenty of memory that would get dropped under pressure but just isn't accounted reclaimable. One example of this is dying cgroups pinned by some page cache. A previous case was auxiliary path name memory associated with dentries; we have since annotated those allocations to avoid overcommit failures (see d79f7aa496fc ("mm: treat indirectly reclaimable memory as free in overcommit logic")). But trying to classify all allocated memory reliably as reclaimable and unreclaimable is a bit of a fool's errand. There could be a myriad of dependencies that constantly change with kernel versions. It becomes even more questionable of an effort when considering how this estimate of available memory is used: it's not compared to the system-wide allocated virtual memory in any way. It's not even compared to the allocating process's address space. It's compared to the single allocation request at hand! So we have an elaborate left-hand side of the equation that tries to assess the exact breathing room the system has available down to a page - and then compare it to an isolated allocation request with no additional context. We could fail an allocation of N bytes, but for two allocations of N/2 bytes we'd do this elaborate dance twice in a row and then still let N bytes of virtual memory through. This doesn't make a whole lot of sense. Let's take a step back and look at the actual goal of the heuristic. From the documentation: Heuristic overcommit handling. Obvious overcommits of address space are refused. Used for a typical system. It ensures a seriously wild allocation fails while allowing overcommit to reduce swap usage. root is allowed to allocate slightly more memory in this mode. This is the default. If all we want to do is catch clearly bogus allocation requests irrespective of the general virtual memory situation, the physical memory counter-part doesn't need to be that complicated, either. When in GUESS mode, catch wild allocations by comparing their request size to total amount of ram and swap in the system. Link: http://lkml.kernel.org/r/20190412191418.26333-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:21:50 +00:00
long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
allowed -= min_t(long, mm->total_vm / 32, reserve);
}
if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
error:
vm_unacct_memory(pages);
return -ENOMEM;
}
/**
* get_cmdline() - copy the cmdline value to a buffer.
* @task: the task whose cmdline value to copy.
* @buffer: the buffer to copy to.
* @buflen: the length of the buffer. Larger cmdline values are truncated
* to this length.
*
* Return: the size of the cmdline field copied. Note that the copy does
* not guarantee an ending NULL byte.
*/
int get_cmdline(struct task_struct *task, char *buffer, int buflen)
{
int res = 0;
unsigned int len;
struct mm_struct *mm = get_task_mm(task);
unsigned long arg_start, arg_end, env_start, env_end;
if (!mm)
goto out;
if (!mm->arg_end)
goto out_mm; /* Shh! No looking before we're done */
prctl_set_mm: downgrade mmap_sem to read lock The commit a3b609ef9f8b ("proc read mm's {arg,env}_{start,end} with mmap semaphore taken.") added synchronization of reading argument/environment boundaries under mmap_sem. Later commit 88aa7cc688d4 ("mm: introduce arg_lock to protect arg_start|end and env_start|end in mm_struct") avoided the coarse use of mmap_sem in similar situations. But there still remained two places that (mis)use mmap_sem. get_cmdline should also use arg_lock instead of mmap_sem when it reads the boundaries. The second place that should use arg_lock is in prctl_set_mm. By protecting the boundaries fields with the arg_lock, we can downgrade mmap_sem to reader lock (analogous to what we already do in prctl_set_mm_map). [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20190502125203.24014-3-mkoutny@suse.com Fixes: 88aa7cc688d4 ("mm: introduce arg_lock to protect arg_start|end and env_start|end in mm_struct") Signed-off-by: Michal Koutný <mkoutny@suse.com> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com> Co-developed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Cyrill Gorcunov <gorcunov@gmail.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Cc: Mateusz Guzik <mguzik@redhat.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-01 05:30:19 +00:00
spin_lock(&mm->arg_lock);
arg_start = mm->arg_start;
arg_end = mm->arg_end;
env_start = mm->env_start;
env_end = mm->env_end;
prctl_set_mm: downgrade mmap_sem to read lock The commit a3b609ef9f8b ("proc read mm's {arg,env}_{start,end} with mmap semaphore taken.") added synchronization of reading argument/environment boundaries under mmap_sem. Later commit 88aa7cc688d4 ("mm: introduce arg_lock to protect arg_start|end and env_start|end in mm_struct") avoided the coarse use of mmap_sem in similar situations. But there still remained two places that (mis)use mmap_sem. get_cmdline should also use arg_lock instead of mmap_sem when it reads the boundaries. The second place that should use arg_lock is in prctl_set_mm. By protecting the boundaries fields with the arg_lock, we can downgrade mmap_sem to reader lock (analogous to what we already do in prctl_set_mm_map). [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20190502125203.24014-3-mkoutny@suse.com Fixes: 88aa7cc688d4 ("mm: introduce arg_lock to protect arg_start|end and env_start|end in mm_struct") Signed-off-by: Michal Koutný <mkoutny@suse.com> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com> Co-developed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Cyrill Gorcunov <gorcunov@gmail.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Cc: Mateusz Guzik <mguzik@redhat.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-01 05:30:19 +00:00
spin_unlock(&mm->arg_lock);
len = arg_end - arg_start;
if (len > buflen)
len = buflen;
res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE);
/*
* If the nul at the end of args has been overwritten, then
* assume application is using setproctitle(3).
*/
if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
len = strnlen(buffer, res);
if (len < res) {
res = len;
} else {
len = env_end - env_start;
if (len > buflen - res)
len = buflen - res;
res += access_process_vm(task, env_start,
buffer+res, len,
FOLL_FORCE);
res = strnlen(buffer, res);
}
}
out_mm:
mmput(mm);
out:
return res;
}
int __weak memcmp_pages(struct page *page1, struct page *page2)
{
char *addr1, *addr2;
int ret;
addr1 = kmap_atomic(page1);
addr2 = kmap_atomic(page2);
ret = memcmp(addr1, addr2, PAGE_SIZE);
kunmap_atomic(addr2);
kunmap_atomic(addr1);
return ret;
}
mm: Add mem_dump_obj() to print source of memory block There are kernel facilities such as per-CPU reference counts that give error messages in generic handlers or callbacks, whose messages are unenlightening. In the case of per-CPU reference-count underflow, this is not a problem when creating a new use of this facility because in that case the bug is almost certainly in the code implementing that new use. However, trouble arises when deploying across many systems, which might exercise corner cases that were not seen during development and testing. Here, it would be really nice to get some kind of hint as to which of several uses the underflow was caused by. This commit therefore exposes a mem_dump_obj() function that takes a pointer to memory (which must still be allocated if it has been dynamically allocated) and prints available information on where that memory came from. This pointer can reference the middle of the block as well as the beginning of the block, as needed by things like RCU callback functions and timer handlers that might not know where the beginning of the memory block is. These functions and handlers can use mem_dump_obj() to print out better hints as to where the problem might lie. The information printed can depend on kernel configuration. For example, the allocation return address can be printed only for slab and slub, and even then only when the necessary debug has been enabled. For slab, build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space to the next power of two or use the SLAB_STORE_USER when creating the kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create() if more focused use is desired. Also for slub, use CONFIG_STACKTRACE to enable printing of the allocation-time stack trace. Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: <linux-mm@kvack.org> Reported-by: Andrii Nakryiko <andrii@kernel.org> [ paulmck: Convert to printing and change names per Joonsoo Kim. ] [ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ] [ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ] [ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ] [ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ] [ paulmck: Explicitly check for small pointers per Naresh Kamboju. ] Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-08 01:41:02 +00:00
#ifdef CONFIG_PRINTK
mm: Add mem_dump_obj() to print source of memory block There are kernel facilities such as per-CPU reference counts that give error messages in generic handlers or callbacks, whose messages are unenlightening. In the case of per-CPU reference-count underflow, this is not a problem when creating a new use of this facility because in that case the bug is almost certainly in the code implementing that new use. However, trouble arises when deploying across many systems, which might exercise corner cases that were not seen during development and testing. Here, it would be really nice to get some kind of hint as to which of several uses the underflow was caused by. This commit therefore exposes a mem_dump_obj() function that takes a pointer to memory (which must still be allocated if it has been dynamically allocated) and prints available information on where that memory came from. This pointer can reference the middle of the block as well as the beginning of the block, as needed by things like RCU callback functions and timer handlers that might not know where the beginning of the memory block is. These functions and handlers can use mem_dump_obj() to print out better hints as to where the problem might lie. The information printed can depend on kernel configuration. For example, the allocation return address can be printed only for slab and slub, and even then only when the necessary debug has been enabled. For slab, build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space to the next power of two or use the SLAB_STORE_USER when creating the kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create() if more focused use is desired. Also for slub, use CONFIG_STACKTRACE to enable printing of the allocation-time stack trace. Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: <linux-mm@kvack.org> Reported-by: Andrii Nakryiko <andrii@kernel.org> [ paulmck: Convert to printing and change names per Joonsoo Kim. ] [ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ] [ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ] [ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ] [ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ] [ paulmck: Explicitly check for small pointers per Naresh Kamboju. ] Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-08 01:41:02 +00:00
/**
* mem_dump_obj - Print available provenance information
* @object: object for which to find provenance information.
*
* This function uses pr_cont(), so that the caller is expected to have
* printed out whatever preamble is appropriate. The provenance information
* depends on the type of object and on how much debugging is enabled.
* For example, for a slab-cache object, the slab name is printed, and,
* if available, the return address and stack trace from the allocation
* and last free path of that object.
mm: Add mem_dump_obj() to print source of memory block There are kernel facilities such as per-CPU reference counts that give error messages in generic handlers or callbacks, whose messages are unenlightening. In the case of per-CPU reference-count underflow, this is not a problem when creating a new use of this facility because in that case the bug is almost certainly in the code implementing that new use. However, trouble arises when deploying across many systems, which might exercise corner cases that were not seen during development and testing. Here, it would be really nice to get some kind of hint as to which of several uses the underflow was caused by. This commit therefore exposes a mem_dump_obj() function that takes a pointer to memory (which must still be allocated if it has been dynamically allocated) and prints available information on where that memory came from. This pointer can reference the middle of the block as well as the beginning of the block, as needed by things like RCU callback functions and timer handlers that might not know where the beginning of the memory block is. These functions and handlers can use mem_dump_obj() to print out better hints as to where the problem might lie. The information printed can depend on kernel configuration. For example, the allocation return address can be printed only for slab and slub, and even then only when the necessary debug has been enabled. For slab, build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space to the next power of two or use the SLAB_STORE_USER when creating the kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create() if more focused use is desired. Also for slub, use CONFIG_STACKTRACE to enable printing of the allocation-time stack trace. Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: <linux-mm@kvack.org> Reported-by: Andrii Nakryiko <andrii@kernel.org> [ paulmck: Convert to printing and change names per Joonsoo Kim. ] [ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ] [ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ] [ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ] [ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ] [ paulmck: Explicitly check for small pointers per Naresh Kamboju. ] Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-08 01:41:02 +00:00
*/
void mem_dump_obj(void *object)
{
const char *type;
if (kmem_valid_obj(object)) {
kmem_dump_obj(object);
return;
}
if (vmalloc_dump_obj(object))
return;
if (virt_addr_valid(object))
type = "non-slab/vmalloc memory";
else if (object == NULL)
type = "NULL pointer";
else if (object == ZERO_SIZE_PTR)
type = "zero-size pointer";
else
type = "non-paged memory";
pr_cont(" %s\n", type);
mm: Add mem_dump_obj() to print source of memory block There are kernel facilities such as per-CPU reference counts that give error messages in generic handlers or callbacks, whose messages are unenlightening. In the case of per-CPU reference-count underflow, this is not a problem when creating a new use of this facility because in that case the bug is almost certainly in the code implementing that new use. However, trouble arises when deploying across many systems, which might exercise corner cases that were not seen during development and testing. Here, it would be really nice to get some kind of hint as to which of several uses the underflow was caused by. This commit therefore exposes a mem_dump_obj() function that takes a pointer to memory (which must still be allocated if it has been dynamically allocated) and prints available information on where that memory came from. This pointer can reference the middle of the block as well as the beginning of the block, as needed by things like RCU callback functions and timer handlers that might not know where the beginning of the memory block is. These functions and handlers can use mem_dump_obj() to print out better hints as to where the problem might lie. The information printed can depend on kernel configuration. For example, the allocation return address can be printed only for slab and slub, and even then only when the necessary debug has been enabled. For slab, build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space to the next power of two or use the SLAB_STORE_USER when creating the kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create() if more focused use is desired. Also for slub, use CONFIG_STACKTRACE to enable printing of the allocation-time stack trace. Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: <linux-mm@kvack.org> Reported-by: Andrii Nakryiko <andrii@kernel.org> [ paulmck: Convert to printing and change names per Joonsoo Kim. ] [ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ] [ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ] [ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ] [ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ] [ paulmck: Explicitly check for small pointers per Naresh Kamboju. ] Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-08 01:41:02 +00:00
}
EXPORT_SYMBOL_GPL(mem_dump_obj);
#endif
mm: introduce page_offline_(begin|end|freeze|thaw) to synchronize setting PageOffline() A driver might set a page logically offline -- PageOffline() -- and turn the page inaccessible in the hypervisor; after that, access to page content can be fatal. One example is virtio-mem; while unplugged memory -- marked as PageOffline() can currently be read in the hypervisor, this will no longer be the case in the future; for example, when having a virtio-mem device backed by huge pages in the hypervisor. Some special PFN walkers -- i.e., /proc/kcore -- read content of random pages after checking PageOffline(); however, these PFN walkers can race with drivers that set PageOffline(). Let's introduce page_offline_(begin|end|freeze|thaw) for synchronizing. page_offline_freeze()/page_offline_thaw() allows for a subsystem to synchronize with such drivers, achieving that a page cannot be set PageOffline() while frozen. page_offline_begin()/page_offline_end() is used by drivers that care about such races when setting a page PageOffline(). For simplicity, use a rwsem for now; neither drivers nor users are performance sensitive. Link: https://lkml.kernel.org/r/20210526093041.8800-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Aili Yao <yaoaili@kingsoft.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jiri Bohac <jbohac@suse.cz> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Roman Gushchin <guro@fb.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Steven Price <steven.price@arm.com> Cc: Wei Liu <wei.liu@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 01:50:14 +00:00
/*
* A driver might set a page logically offline -- PageOffline() -- and
* turn the page inaccessible in the hypervisor; after that, access to page
* content can be fatal.
*
* Some special PFN walkers -- i.e., /proc/kcore -- read content of random
* pages after checking PageOffline(); however, these PFN walkers can race
* with drivers that set PageOffline().
*
* page_offline_freeze()/page_offline_thaw() allows for a subsystem to
* synchronize with such drivers, achieving that a page cannot be set
* PageOffline() while frozen.
*
* page_offline_begin()/page_offline_end() is used by drivers that care about
* such races when setting a page PageOffline().
*/
static DECLARE_RWSEM(page_offline_rwsem);
void page_offline_freeze(void)
{
down_read(&page_offline_rwsem);
}
void page_offline_thaw(void)
{
up_read(&page_offline_rwsem);
}
void page_offline_begin(void)
{
down_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_begin);
void page_offline_end(void)
{
up_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_end);
#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
void flush_dcache_folio(struct folio *folio)
{
long i, nr = folio_nr_pages(folio);
for (i = 0; i < nr; i++)
flush_dcache_page(folio_page(folio, i));
}
EXPORT_SYMBOL(flush_dcache_folio);
#endif